A method, system, medium and product for processing duty data of a smart camp

Abstract

A kind of method, system, medium and product of data processing of duty of wisdom camp, in the method, system first obtains the attribute information of current execution task and to-be-executed task, generates the vector reflecting the completion state of current task and the vector of next task admission requirement. By comparing the two vectors, determine the conflict items that need to be adjusted, and find the corresponding state recovery action and its required duration. Combined with the physical travel time between the two task locations, the total transition time is calculated. According to the latest start time of the second task and the transition time, the system judges the key end time point of the first task, and decides whether to generate a scheduling instruction containing state recovery action according to the key end time point. The present application is used to improve the prediction accuracy of the start time of subsequent task, reduce the service response delay risk caused by the personnel unable to arrive at the designated point in time.

Description

Technical Field

[0001] This application belongs to the field of electronic digital data processing, and in particular relates to a method, system, medium and product for processing service data in a smart barracks. Background Technology

[0002] With the large-scale expansion of various large-scale integrated smart parks and enterprise operation bases, the processing of service data within the parks has become a fundamental support for ensuring the orderly operation of various businesses. This field covers diversified businesses such as facility inspection, environmental maintenance, security shifts, and material distribution. The precision and synergy of its data processing are directly related to the park's operating costs and service quality.

[0003] Among related technologies, smart park management solutions generally adopt a centralized processing technology based on digital work order flow. This technology builds a unified duty management service platform, transforms various offline businesses into standardized electronic work order processes, uses a relational database to structurally store personnel files, scheduling rules, and task logs, and uses mobile applications to issue and execute task instructions. This enables online flow and preliminary statistical analysis of duty data, allowing managers to intuitively query the current progress and historical records of various tasks through the system interface, thereby improving the standardization and transparency of daily duty management in the park to a certain extent.

[0004] When assigning tasks, the aforementioned technologies typically rely on the logic that resource release is considered complete upon task completion. For example, when a maintenance worker completes equipment repair in the eastern area of ​​the park and clicks "complete" in the system, the system immediately marks it as available and may then assign the next urgent task in the western area. However, in actual operations, there is an objectively significant physical displacement time and hidden time consumption such as tool reorganization when withdrawing from the eastern work site and transferring to the western site. When processing such continuous service data, the generated planned timeline deviates from the actual executable timeline. This deviation has a cumulative effect when tasks are concentrated, thereby reducing the accuracy of predicting the start time of subsequent tasks and increasing the risk of service response delays due to personnel not being able to arrive at the designated location on time. Summary of the Invention

[0005] This application provides a smart camp service data processing method, system, medium, and product to improve the accuracy of predicting the start time of subsequent tasks and reduce the risk of service response delays caused by personnel failing to arrive at designated locations on time.

[0006] In a first aspect, this application provides a method for processing duty data in a smart barracks, which obtains a first task attribute set for a first duty task that is being executed and a second task attribute set for a second duty task to be executed. The first task attribute set includes the end position of the first task and a task type identifier, and the second task attribute set includes the start position of the second task, a task type identifier, and the latest start time.

[0007] A completion status vector is generated based on the first task attribute set. The completion status vector consists of the first equipment holding list and the first physiological load level. An access requirement vector is generated based on the second task attribute set. The access requirement vector consists of the second equipment requirement list and the second physiological load limit.

[0008] The completion state vector is compared with the admission requirement vector to identify state conflict items, which include equipment mismatch items or physiological load exceeding limits.

[0009] Based on the state conflict item, the corresponding state recovery action is matched from the preset duty transition rule table, and the state transition time required to execute the state recovery action is obtained;

[0010] Calculate the physical travel time based on the end position of the first task and the start position of the second task;

[0011] The sum of the state transition duration and the physical passage duration is determined as the comprehensive transition time window;

[0012] The critical disengagement time of the first mission is calculated by subtracting the comprehensive transition time window from the latest start time of the second mission.

[0013] Obtain the estimated completion time of the first duty task. If the estimated completion time is earlier than or equal to the critical departure time, generate a scheduling instruction that includes state recovery actions and lock the second duty task as the next execution item.

[0014] By adopting the above technical solution, and by acquiring the attribute sets of the first and second service tasks, generating and comparing the completion status vector with the access requirement vector, the system can identify status conflicts related to equipment matching and physiological load. Based on the identified conflicts, the system matches the corresponding status recovery actions from a preset rule table and calculates the required duration, combining this with the physical passage time to obtain a comprehensive transition time window. Subtracting the latest start time from the comprehensive transition time window yields the critical disengagement time of the first task, thus determining whether the task switching conditions are met. This processing method considers multiple dimensions such as personnel equipment status, physiological state, and physical distance, making the task switching time calculation more accurate and reducing task delays caused by equipment incompatibility or personnel physiological discomfort. By planning status recovery actions in advance, the system improves the continuity and smoothness of task handover, increases the accuracy of predicting the start time of subsequent tasks, and reduces the risk of service response delays caused by personnel failing to arrive at designated locations on time.

[0015] In conjunction with some implementation methods of the first aspect, in some implementation methods, a completion state vector is generated based on the first task attribute set, specifically including:

[0016] The duration of the task and environmental stress parameters are extracted from the first task attribute set. The environmental stress parameters include the temperature value and noise decibel value of the task area.

[0017] Using a pre-defined physiological energy consumption accumulation model, the basal metabolic rate corresponding to the task type identifier is used as the base, and the environmental stress parameters are mapped to nonlinear gain coefficients. The cumulative fatigue value is obtained by integrating the task duration.

[0018] The cumulative fatigue values ​​are mapped to a preset fatigue grading table to determine the first physiological load level;

[0019] The first physiological load level is combined with the list of standard equipment retrieved based on the task type identifier to generate a completion status vector.

[0020] By employing the aforementioned technical solution, and analyzing task duration and environmental stress parameters, a pre-defined physiological energy consumption accumulation model is used to calculate cumulative fatigue values. The model uses the basal metabolic rate corresponding to the task type as the base, while converting environmental stress parameters such as temperature and noise levels into nonlinear gain coefficients, and performing integration calculations over the task duration. By mapping the calculated cumulative fatigue values ​​to a pre-defined fatigue grading table, the system can more accurately assess the physiological load level of personnel. This calculation method, which considers the influence of environmental factors, improves the accuracy of assessing the fatigue state of on-duty personnel, making the determination of physiological load levels more consistent with reality. Combined with the standard equipment list corresponding to the task type, the generated completion state vector can more comprehensively reflect the state information of on-duty personnel, enhancing the rationality of subsequent task allocation decisions.

[0021] In conjunction with some implementation methods of the first aspect, in some implementation methods, a completion state vector is generated based on the first task attribute set, specifically including:

[0022] Obtain the initial equipment list for the first duty mission, and divide the items in the initial equipment list into consumable equipment items and portable equipment items according to the mission type identifier;

[0023] Execute the equipment status inheritance logic to remove consumable equipment items from the initial equipment list, retaining only the held equipment items;

[0024] Detect the area attribute of the end location of the first task. If the area attribute is marked as a contaminated area or a classified area, then attach the corresponding status handling label to the equipment item.

[0025] The first equipment holding list is generated by removing and tagging the held equipment items, and combined with the first physiological load level to form a completion status vector.

[0026] By adopting the above technical solutions, classifying the initial equipment list into consumable and held equipment items, and executing equipment status inheritance logic, the system can more accurately track and record the actual status of held equipment. By detecting the regional attributes of the mission's end location, and attaching corresponding status handling tags to equipment items in contaminated or classified areas, the system improves its ability to identify post-use handling requirements for equipment in special areas. This refined management method of equipment status improves the traceability of equipment usage status and enhances the effectiveness of pollution prevention and confidentiality management during equipment transfer. By combining the processed held equipment list with physiological load levels, the generated completion status vector more closely reflects the actual situation, improving the accuracy of duty management decisions.

[0027] In conjunction with some implementations of the first aspect, in some implementations, after locking the second service task as the next execution item, the method further includes:

[0028] When the target object performs physical passage, the real-time physiological parameters of the target object are acquired at a preset sampling frequency;

[0029] Based on the real-time physiological parameter change trend and the time difference between the current time and the scheduled start time of the second duty mission, calculate the predicted values ​​of the target object's physiological parameters at the scheduled start time.

[0030] If the predicted values ​​of physiological parameters are not within the range of the threshold limits for admission physiological indicators, then an intervention control instruction for the physical access path is generated.

[0031] In response to intervention control commands, the information display density of the augmented reality device worn by the target object is reduced, and the display color temperature parameters of the augmented reality device are adjusted;

[0032] Send adjustment signals to environmental control equipment located on the physical passageway to control the environmental control equipment to reduce the brightness of the light or output white noise.

[0033] By employing the aforementioned technical solution, and through real-time collection of physiological parameters and analysis of their changing trends, combined with time difference calculations to predict physiological parameter values, dynamic monitoring of the personnel's condition is achieved. When the predicted value exceeds the threshold range, the system adjusts the display density and color temperature parameters of the augmented reality device, as well as controlling the brightness and white noise output of the environmental equipment, forming a dynamic intervention and adjustment mechanism. This prediction-based proactive intervention method improves the physiological state regulation effect of personnel during task handover and enhances the targeted nature of state recovery. Through the coordinated adjustment of environmental parameters, the system improves the overall effect of physiological state regulation, enhances the adaptability of personnel when arriving at the next task point, and strengthens the safety during task handover.

[0034] In conjunction with some implementation methods of the first aspect, in some implementation methods, based on the changing trends of real-time physiological parameters and the time difference between the current time and the predetermined start time of the second duty mission, the predicted values ​​of the target object's physiological parameters at the predetermined start time are calculated, specifically including:

[0035] Calculate the difference between the scheduled start time and the current time to obtain the remaining recovery time;

[0036] Extract real-time physiological parameters within the most recent preset time period to construct a physiological parameter time series;

[0037] Linear regression analysis was performed on the time series of physiological parameters to obtain the slope of the recovery rate, which represents the trend of change.

[0038] Based on the real-time physiological parameters at the current moment, linear extrapolation is performed using the recovery rate slope and remaining recovery time to obtain the predicted values ​​of the physiological parameters of the target object at the predetermined start time.

[0039] By employing the aforementioned technical solution, the remaining recovery time is calculated, and linear regression analysis is performed on the time series of physiological parameters from the most recent period to obtain the slope of the recovery rate. This slope is then combined with current physiological parameters for linear extrapolation, thereby obtaining the predicted physiological parameters of the target subject at the predetermined start time. This real-time data-based prediction method considers individual differences and the dynamic changes in the current state, thus improving the accuracy of physiological parameter prediction. Because the prediction results are closer to the actual situation, the system can more accurately determine whether the target subject meets the admission physiological requirements, reducing unnecessary interventions or missed diagnoses due to prediction bias. By improving prediction accuracy, the system ensures the quality of task execution while reducing interference with the target subject's normal activities, thereby enhancing the targeting and effectiveness of intervention measures.

[0040] In conjunction with some embodiments of the first aspect, in some embodiments, after reducing the information display density of the augmented reality device worn by the target object and adjusting the display color temperature parameters of the augmented reality device in response to an intervention control command, the method further includes:

[0041] While maintaining the execution of intervention control commands, external field-of-view images are acquired through augmented reality devices;

[0042] Risk target identification is performed on external field-of-view images to determine the current environmental safety level of the target object;

[0043] If the environmental safety level is alarm state, an interrupt command will be generated;

[0044] In response to the interrupt command, the execution of intervention control commands is stopped, and the information display density and display color temperature parameters of the augmented reality device are restored to their initial state.

[0045] By employing the aforementioned technical solution, external field-of-view images are continuously acquired and risk target identification is performed simultaneously with intervention control. The execution status of intervention control commands is dynamically adjusted according to the environmental safety level. This real-time monitoring and dynamic adjustment mechanism enables the system to balance environmental safety factors while ensuring physiological recovery, thus improving the adaptability of intervention control. When a potential risk is detected, the display parameters of the augmented reality device are promptly restored to ensure that the target object receives complete environmental situational information, enhancing the target object's perception and response capabilities to emergencies. This dual-protection mechanism achieves a dynamic balance between improving physiological condition and the safety of maintenance personnel, improving the safety and reliability of intervention control measures during execution.

[0046] In conjunction with some implementations of the first aspect, in some implementations, risk target identification is performed on the external field-of-view image to determine the current environmental safety level of the target object, specifically including:

[0047] Process external field-of-view images using a pre-trained object detection model;

[0048] If a target of a preset category or a dynamic target whose speed exceeds a preset safety threshold is identified in the external field of view, the environmental safety level is determined to be an alarm state.

[0049] If no target or moving target is identified in the external field of view, the environmental safety level is determined to be safe.

[0050] By employing the aforementioned technical solution, a pre-trained target detection model is used to process external field-of-view images. Environmental safety levels are assessed by identifying preset target categories and dynamic targets exceeding safety thresholds. This computer vision-based automated identification method improves the timeliness and accuracy of risk identification, reducing delays and misjudgments that may arise from manual judgment. By combining target detection with dynamic feature analysis, the system can more comprehensively assess potential risks in the environment, increasing the coverage of risk identification. This intelligent risk assessment method enables the system to identify potential threats more quickly, improving the timeliness of early warning responses and reducing security risks caused by untimely or inaccurate risk identification.

[0051] Secondly, embodiments of this application provide a smart camp service data processing system, which includes: one or more processors and a memory; the memory is coupled to one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to cause the system to perform the method described in the first aspect and any possible implementation thereof.

[0052] Thirdly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a system, cause the system to perform the method described in the first aspect and any possible implementation thereof.

[0053] Fourthly, embodiments of this application provide a computer program product that, when run on a system, causes the system to execute the method described in any possible implementation of the first aspect.

[0054] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0055] 1. This application provides a smart camp service data processing method. By acquiring the attribute sets of the first and second service tasks, generating and comparing the completion status vector with the access requirement vector, the system can identify status conflicts related to equipment matching and physiological load. Based on the identified conflicts, the system matches corresponding status recovery actions from a preset rule table and calculates the required duration, combining this with physical passage time to obtain a comprehensive transition time window. Subtracting the latest start time from the comprehensive transition time window yields the critical departure time of the first task, thus determining whether the task switching conditions are met. This processing method considers multiple dimensions such as personnel equipment status, physiological state, and physical distance, making the task switching time calculation more accurate and reducing task delays caused by equipment mismatch or personnel physiological discomfort. By planning status recovery actions in advance, the system improves the continuity and smoothness of task handover, increases the accuracy of predicting the start time of subsequent tasks, and reduces the risk of service response delays caused by personnel failing to arrive at designated locations on time.

[0056] 2. This application provides a smart camp duty data processing method. By collecting physiological parameters in real time and analyzing their changing trends, and combining the time difference to calculate predicted values ​​of physiological parameters, dynamic monitoring of the status of on-duty personnel is achieved. When the predicted value exceeds the access threshold range, the system adjusts the display density and color temperature parameters of the augmented reality device, as well as controls the brightness and white noise output of the environmental device, forming a dynamic intervention and adjustment mechanism. This prediction-based proactive intervention method improves the physiological state regulation effect of on-duty personnel during task handover and enhances the targeted nature of state recovery. Through the coordinated adjustment of environmental parameters, the system improves the overall effect of physiological state regulation, enhances the adaptability of on-duty personnel when arriving at the next task point, and strengthens the safety during task handover. Attached Figure Description

[0057] Figure 1 This is a flowchart illustrating a smart camp duty data processing method in an embodiment of this application.

[0058] Figure 2 This is another flowchart illustrating a smart camp service data processing method in an embodiment of this application.

[0059] Figure 3 This is a schematic diagram of the physical device structure of a smart camp service data processing system provided in an embodiment of this application. Detailed Implementation

[0060] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0061] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0062] The following example is used in conjunction with Figure 1 The present application describes a method for processing duty data in a smart barracks according to an embodiment of the present application:

[0063] Please see Figure 1 This is a flowchart illustrating a smart camp service data processing method in an embodiment of this application.

[0064] S101. Obtain the first task attribute set of the first duty task currently being executed and the second task attribute set of the second duty task to be executed;

[0065] The system acquires the first task attribute set of the first duty task currently being executed and the second task attribute set of the second duty task to be executed. The first task attribute set includes the end position and task type identifier of the first task, while the second task attribute set includes the start position, task type identifier, and latest start time of the second task. The first duty task refers to the task activity being carried out by personnel or execution units as monitored by the system at the current time. This can be various camp duty tasks such as patrolling, sentry duty, and material handling. The first task attribute set is a data set describing the characteristics of the first duty task, and this set includes at least the end position and task type identifier of the first task. The end position of the first task refers to the geographical coordinates or area code when the first duty task is expected to be completed. The task type identifier is a code or label used to uniquely distinguish the type of duty, such as identifying whether the task belongs to a high-intensity physical task, a precision operation task, or a general guard duty task. The second duty task to be executed refers to a task that immediately follows the first duty task in the time sequence and is planned to be carried out by the same execution entity. The second task attribute set includes the start position, task type identifier, and latest start time of the second task. The starting location of the second task refers to the geographical coordinates or area code of the executing entity required to initiate the second duty task. The latest start time refers to the deadline at which the task must be started to ensure that the second duty task is completed on schedule or without delaying the overall duty plan. The system first retrieves the currently ongoing duty activity records in real time through its internal task scheduling interface or database query commands as the first duty task, and extracts its associated attribute data to form the first task attribute set. Simultaneously, the system retrieves the next pending item assigned to the same executing entity from the task queue, defines it as the second duty task, and extracts its corresponding attribute data to form the second task attribute set. This process ensures that the system grasps the key contextual information before and after the task switch, laying the foundation for subsequent status assessment and conflict detection.

[0066] In the specific implementation of obtaining task attribute sets, the system can adopt an event-driven message queue mechanism. When the duty management subsystem publishes a task update event, the listening module automatically captures the event and parses the first and second task attribute sets from the JSON-formatted task load data. The parsing process uses predefined key-value pair mapping rules to directly extract information such as location coordinates, task IDs, and timestamps. Another implementation method is to use a timed polling mechanism. The system periodically sends SQL query requests to the central duty database, querying the current status table and the pending task table based on the unique identity ID of the executor. The query results are returned in the form of a structured dataset. The system uses data cleaning algorithms to remove redundant fields, retaining only core attributes such as location, type, and time constraints, thereby constructing standardized first and second task attribute sets. Both methods can ensure the real-time performance and accuracy of the data. The former is suitable for high-concurrency scenarios, while the latter is suitable for resource-constrained embedded environments.

[0067] S102. Generate a completion status vector based on the first task attribute set. The completion status vector consists of the first equipment holding list and the first physiological load level. Generate an access requirement vector based on the second task attribute set. The access requirement vector consists of the second equipment requirement list and the second physiological load limit.

[0068] A completion status vector is generated based on the first task attribute set. The completion status vector consists of the first equipment holding list and the first physiological load level. Specifically, it can be achieved in at least the following two ways:

[0069] The mission duration and environmental stress parameters are extracted from the first mission attribute set. The environmental stress parameters include the temperature and noise level of the mission area. Using a preset physiological energy consumption accumulation model, the basal metabolic rate corresponding to the mission type identifier is used as the base, and the environmental stress parameters are mapped to nonlinear gain coefficients. The cumulative fatigue value is obtained by integrating the mission duration. The cumulative fatigue value is mapped to a preset fatigue grading table to determine the first physiological load level. The first physiological load level is combined with the standard equipment list retrieved based on the mission type identifier to generate a completion state vector.

[0070] Alternatively, obtain the initial equipment list for the first duty mission, and divide the items in the initial equipment list into consumable equipment items and held equipment items according to the mission type identifier; execute the equipment state inheritance logic to remove consumable equipment items from the initial equipment list, retaining only held equipment items; detect the area attribute of the end location of the first mission, and if the area attribute is marked as a contaminated area or a classified area, attach the corresponding status disposal tag to the held equipment items; generate the first equipment holding list from the held equipment items after removal and tag attachment processing, and combine it with the first physiological load level to form a completion state vector.

[0071] The completion status vector is a multi-dimensional data structure used to digitally represent the comprehensive state of the executing entity upon completing the first duty mission. Its core components include the first equipment holding list and the first physiological load level. The first equipment holding list details all equipment and supplies carried by the executing entity at the end of the mission, including but not limited to weapons, communication equipment, and protective gear. The first physiological load level is a graded description of the executing entity's physical fatigue, stress level, or physical exertion at the end of the mission, typically divided into multiple levels such as low load, medium load, high load, and extreme load. The access requirement vector is a digital description of the conditions for initiating the second duty mission, including the second equipment requirement list and the second physiological load limit. The second equipment requirement list lists the supplies that must be equipped for performing the second mission. The second physiological load limit refers to the maximum fatigue or stress level that personnel performing the second mission can withstand. The system derives the completion status vector through a calculation model based on information such as mission duration and environmental parameters in the first mission attribute set; simultaneously, it queries standard operating procedures based on the type identifier in the second mission attribute set to generate the access requirement vector. This step transforms the abstract task description into a quantifiable and comparable mathematical vector, providing a unified metric for subsequent conflict detection.

[0072] For the refined technical solution of generating a completion state vector based on the first task attribute set, the first specific implementation method is based on the calculation of a physiological energy consumption accumulation model. The system first extracts the task duration and environmental stress parameters from the first task attribute set. The environmental stress parameters specifically include the real-time temperature value and ambient noise decibel value of the task area. The system calls a preset physiological energy consumption accumulation model, which uses the basal metabolic rate corresponding to the task type identifier as the calculation base. Subsequently, fuzzy logic algorithms or lookup tables are used to map the temperature value and noise decibel value to nonlinear gain coefficients; for example, a larger gain coefficient corresponds to a high-temperature, high-noise environment. The system performs time integration on the task duration and calculates the cumulative fatigue value by combining the base and the gain coefficient. Finally, this value is mapped to a preset fatigue grading table to determine the first physiological load level, and combined with the standard equipment list retrieved according to the task type to construct the completion state vector. The preset physiological energy consumption accumulation model is a multi-dimensional weighted integral calculation system based on ergonomics and exercise physiology. Using the basal metabolic rate (METs) of the task type as the calculation basis, this model employs a nonlinear gain function to transform environmental stress factors such as temperature and noise into amplification factors on energy consumption. It then simulates the dynamic accumulation of fatigue over time through integral calculations over the duration of the task. The model's functionality stems from its scientific quantification of the combined impact of task intensity, environmental stress, and accumulated time on human function, transforming qualitative work activities into objective physiological cost values. This provides precise data support for subsequent assessments of personnel's ability to continue performing tasks.

[0073] The second implementation focuses on the dynamic tracking of equipment status. The system obtains the initial equipment list for the first mission and, based on the mission type identifier, uses a classification algorithm to divide the items in the list into consumable equipment (such as ammunition and first-aid kits) and held equipment (such as firearms and radios). Then, it executes equipment status inheritance logic, removing consumable equipment from the list and retaining only held equipment. The system further detects the regional attributes of the first mission's end location. If the area is marked as a contaminated or classified area in the GIS system, a rule engine is used to attach a "pending decontamination" or "pending declassification" status label to the held equipment. Finally, the processed held equipment is used to generate the first equipment holding list, which, combined with the first physiological load level estimated through sensor data or models, forms the completion status vector.

[0074] S103. Compare the completed state vector with the admission requirement vector to determine the state conflict items;

[0075] The system compares the completion status vector with the access requirements vector to identify status conflict items, including equipment mismatch items and physiological overload exceeding limits. Status conflict items refer to inconsistencies or violations between the current state (completion status) of the executing entity and the access conditions (access requirements) of the next task during task handover. These conflicts are mainly divided into two categories: equipment mismatch items and physiological overload exceeding limits. Equipment mismatch items refer to the difference between the first equipment holding list and the second equipment requirement list, including the lack of necessary equipment (missing items), carrying redundant equipment that affects operations (redundant items), or equipment not meeting requirements (such as carrying equipment from a contaminated area into a clean area). Physiological overload exceeding limits refers to a situation where the first physiological overload level exceeds the second physiological overload limit, meaning that the personnel are too fatigued to safely or efficiently perform the next task. When performing the comparison operation, the system performs logical operations on the equipment component and the physiological component in the vector. For the equipment component, the system performs set difference operations; for the physiological component, the system performs numerical comparison operations. Once a discrepancy or exceeding of limits is detected, the system marks these specific discrepancies as state conflict items and generates a conflict report as the basis for subsequent decision-making.

[0076] The first technique for implementing the comparison process is a rule-based expert system matching method. The system pre-loads a service conversion rule base, which defines the compatibility matrix of various equipment and the tolerance of physiological indicators. The system traverses each equipment element in the completed state vector, searching for a corresponding item in the admission requirement vector. If no match is found or the state label (e.g., "contaminated") does not match the requirement, the conflict judgment logic in the rule base is triggered, outputting a specific description of the equipment mismatch. For physiological load, the system directly compares the level values; if the former is greater than the latter, a physiological load exceeding limit alarm is output. The second technique is a vector space distance calculation method. The system converts the equipment list into a high-dimensional sparse vector using one-hot encoding and normalizes the physiological load levels into scalars. The system calculates the Hamming distance or Jaccard distance between two equipment vectors; a non-zero distance represents an equipment mismatch. Simultaneously, the algebraic difference of the physiological load values ​​is calculated; a positive difference represents the degree of physiological load exceeding limit. This method is suitable for rapid batch processing of large-scale data and can quickly locate conflict points.

[0077] S104. Based on the state conflict item, match the corresponding state recovery action from the preset duty transition rule table, and obtain the state transition time required to execute the state recovery action;

[0078] The preset duty transition rule table is a relational table or knowledge graph stored in the system database. It defines standard solutions for various specific state conflict items and their corresponding time costs. State recovery actions refer to the specific operations required to eliminate state conflicts and enable the executing entity to meet the second task access criteria, such as "receiving equipment," "returning supplies," "equipment decontamination," "rest and recovery," or "medical treatment." State transition duration refers to the standard time required to execute each of the above recovery actions, which is usually set based on historical statistical data or standard work quotas. The system parses the state conflict items identified in the previous step, uses them as query keys, and retrieves them from the rule table. For equipment mismatches, the system matches corresponding supply allocation actions; for physiological overload, the system matches corresponding rest or treatment plans. The system summarizes all matched actions and accumulates or calculates the time required for these actions in parallel to obtain the total state transition duration.

[0079] The first approach to implementing this step is to use a lookup table combined with a serial accumulation strategy. The system maintains a relational database table with fields including "conflict type," "recovery action," and "standard duration." The system iterates through each state conflict item, executing an SQL query to obtain the corresponding recovery action and duration. If multiple conflicts exist (e.g., both lacking equipment and fatigued), the system assumes these actions must be executed sequentially, so all retrieved durations are directly added together to obtain the total state transition duration. This approach is logically simple and suitable for scenarios where time precision requirements are not high. The second approach is to use a parallel computing strategy based on dependency graphs. The system constructs a directed acyclic graph (DAG) containing all potential recovery actions. Nodes in the graph represent actions, and edges represent dependencies between actions (e.g., "returning old equipment" is required before "receiving new equipment," but "resting" can be performed simultaneously with "waiting for equipment allocation"). The system activates relevant nodes in the graph based on the identified conflict items and uses the Critical Path Method to calculate the longest path time from the start point to the end point. This time is the shortest state transition duration required to execute the state recovery action. This approach takes into account the parallelism of actions, resulting in more accurate calculations that align with actual operational procedures.

[0080] S105. Calculate the physical passage time based on the end position of the first task and the start position of the second task;

[0081] Physical travel time refers to the pure distance traveled by the operator from the end point of the first duty to the start point of the second duty, excluding any intermediate processing or rest time. Both the end point and the start point of the first and second duties are spatial points based on geographic coordinates (such as latitude and longitude) or camp grid coding. The system calls its built-in path planning engine, inputting these two coordinates as the start and end points. The system combines this with digital map data of the camp, which includes road networks, terrain slopes, restricted areas (such as no-entry zones and one-way streets), and average travel speeds on different road sections. The system calculates one or more feasible paths and determines the optimal route based on the shortest or fastest path principle, then calculates the physical travel time by dividing the distance by the speed.

[0082] The first technique for implementing the calculation is the A* (A-Star) search algorithm. The system abstracts the camp map into a weighted graph, where nodes represent intersections or key locations, edges represent roads, and edge weights consider both distance and road condition resistance. The system uses the end position of the first task as the starting node and the start position of the second task as the target node, and uses the heuristic function of the A* algorithm (usually Euclidean distance or Manhattan distance) to quickly search for the path with the minimum cost. Then, the physical travel time is calculated by dividing the total path length by the standard travel speed of the executing entity (such as hikers or vehicles). The second technique combines a navigation mesh with Dijkstra's algorithm. The system pre-divides the traversable area of ​​the camp into polygonal meshes, constructing a navigation mesh data structure. When calculating the time, the system first locates the meshes containing the start and end points, and uses Dijkstra's algorithm to calculate the shortest path between the center points of the meshes. For movement within a mesh, straight-line distance is used for calculation. The system can also adjust the connectivity between grids based on real-time monitoring data (e.g., temporary road closures due to construction), thereby dynamically calculating the physical travel time to adapt to the current road conditions.

[0083] S106. The sum of the state transition duration and the physical passage duration is determined as the comprehensive transition time window;

[0084] The comprehensive transition time window refers to the total necessary time interval from the end of the first duty mission to the point where the executing entity is fully ready and arrives at the second duty mission post. It consists of two main parts: one is the "soft" time (state transition duration) used for handling equipment changes, physiological recovery, etc., and the other is the "hard" time (physical travel time) used for spatial displacement. The system performs an addition operation, summing the state transition duration obtained in step S104 with the physical travel time calculated in step S105. This sum represents the shortest time span required to seamlessly connect the two missions under ideal or anticipated conditions. This time window is a key parameter for subsequent scheduling decisions, directly determining whether the mission chain is continuous and feasible.

[0085] The first method to implement this step is a simple scalar addition operation. The system reads the state transition duration and physical passage duration variables, stored as floating-point numbers or integers (in minutes or seconds), from memory, executes the addition instruction, and assigns the result to the comprehensive transition time window variable. This method is extremely fast and suitable for most common scenarios. The second method is time interval-based addition, taking into account the uncertainty of time. The system represents the state transition duration and physical passage duration as tuples with confidence intervals, such as (fastest time, average time, slowest time). The system performs interval arithmetic operations to calculate the minimum, expected, and maximum values ​​of the comprehensive transition time window. This method not only provides a single value but also the fluctuation range of the time window, providing data support for subsequent risk assessment.

[0086] S107. Subtract the integrated transition time window from the latest start time of the second service mission to calculate the critical disengagement time of the first service mission.

[0087] The critical departure time refers to the latest time at which the executing entity must finish and leave the site of the first task to ensure that the second task is not delayed. This is a backward calculation process. The latest start time of the second task is a hard deadline defined in the task attribute set. The comprehensive transition time window is the total time required to complete the task switchover. The system uses time subtraction to deduct the duration of the comprehensive transition time window from the timestamp of the latest start time; the result is the critical departure time. If the executing entity finishes the first task after this time, the second task will inevitably be delayed, even if all subsequent actions are carried out as planned. Therefore, the critical departure time is a critical threshold for determining whether the first task needs to be terminated early or whether the executing entity needs to be changed.

[0088] The first method to implement this step is to use a standard timestamp library for calculation. The system parses the latest start time of the second duty mission into a Unix timestamp (the number of seconds since January 1, 1970), and converts the integrated transition time window into seconds. After performing the subtraction operation, the difference is converted back to a human-readable date and time format (e.g., YYYY-MM-DDHH:MM:SS) and marked as the critical disengagement time. This method is highly versatile and easy to interact with across systems. The second method is to use a countdown timer. The system sets a virtual countdown timer, with the initial value being the latest start time of the second duty mission. The system sequentially deducts the physical passage time and the duration of each state recovery action from this time point. During the backtracking process, the system can also consider special factors for different time periods (such as nighttime operation coefficients). The final time the countdown timer stops is the critical disengagement time. This method facilitates the visualization of the time consumption composition during the calculation process, which is beneficial for dispatcher monitoring.

[0089] S108. Obtain the estimated completion time of the first service task. If the estimated completion time is earlier than or equal to the critical departure time, generate a scheduling instruction containing state recovery actions and lock the second service task as the next execution item.

[0090] The estimated completion time refers to the task completion time dynamically estimated by the system based on the current progress of the first duty, remaining workload, and the real-time efficiency of the executing entity. The scheduling instruction is a specific operation command sent by the system to the executing entity or terminal device. It not only includes the instruction to "proceed with the second task" but also details the status recovery actions that must be performed during the handover process (e.g., "Please go to point A to return the rifle, then go to point B to rest for 10 minutes"). The locking operation refers to formally assigning the second duty to the executing entity in the task scheduling queue and changing the task status to "assigned" or "locked" to prevent other scheduling processes from preempting the task or the personnel. The system first obtains the estimated completion time of the first task from the task monitoring module and compares it with the critical disengagement time calculated in step S107. If the estimated completion time is less than or equal to the critical disengagement time, it indicates sufficient time and task handover is feasible. At this time, the system automatically encapsulates and issues a scheduling instruction containing specific recovery steps, while simultaneously locking the task relationship in the database.

[0091] The first approach to implementing this step is based on automated triggering logic using conditional judgments. The system writes an IF-THEN logic block: IF(Predicted_End_Time<=Critical_Departure_Time)THEN{Generate_Instruction(Recovery_Actions); Lock_Task(Task_ID_2, User_ID); Send_Notification();}. The estimated completion time is calculated using a linear regression algorithm based on the percentage of task progress already completed. Once the condition is met, the system immediately calls the instruction generation microservice and database transaction lock service to complete the instruction issuance and task locking. The second approach uses a human-computer interaction confirmation mode. The system performs time comparison in the background. When the condition is met, instead of directly issuing the instruction at the front end, it pops up a "Suggested Scheduling Plan" window on the command center's console, displaying the remaining time, recommended recovery action paths, and details of the second task. Only after the commander clicks the "Confirm" button does the system officially generate the instruction and lock the task. This approach adds a manual review step and is suitable for high-risk or highly sensitive duty scenarios.

[0092] In the above embodiments, by acquiring the attribute sets of the first and second service tasks, generating and comparing the completion state vector with the access requirement vector, the system can identify state conflicts related to equipment matching and physiological load. Based on the identified conflicts, the system matches the corresponding state recovery actions from a preset rule table and calculates the required duration, combining this with the physical passage time to obtain a comprehensive transition time window. Subtracting the latest start time from the comprehensive transition time window yields the critical departure time of the first task, thus determining whether the task switching conditions are met. This processing method considers multiple dimensions such as personnel equipment status, physiological state, and physical distance, making the task switching time calculation more accurate and reducing task delays caused by equipment mismatch or personnel physiological discomfort. By planning state recovery actions in advance, the system improves the continuity and smoothness of task handover, increases the accuracy of predicting the start time of subsequent tasks, and reduces the risk of service response delays caused by personnel failing to arrive at designated locations on time.

[0093] In the above embodiments, the system achieves intelligent scheduling of duty handover by analyzing task attributes and calculating time windows. However, in actual execution, the physiological state of personnel may dynamically change during the physical travel time from completing the first task to reaching the second task location, requiring real-time monitoring and adjustment to ensure they meet the entry requirements for the second task. Therefore, this application also provides another method for processing duty data in a smart camp, which is described below in conjunction with... Figure 2 Another method for processing duty data in a smart barracks, as described in this application embodiment, is as follows:

[0094] Please see Figure 2 This is another flowchart illustrating a smart camp service data processing method in an embodiment of this application.

[0095] S201. When the target object performs physical passage, the real-time physiological parameters of the target object are obtained at a preset sampling frequency;

[0096] The system first defines the target as a camp personnel wearing a biometric monitoring terminal who is physically moving between the location of their previous duty and the location of their next duty. Physical movement refers to the act of moving from a starting point to a destination point in geographic space. The preset sampling frequency refers to the number of times the system reads sensor data per unit of time. This frequency can be dynamically adjusted based on the urgency of the task or power management strategies, and is not limited to a fixed value; for example, it can be once per second or multiple times per second. Real-time physiological parameters refer to biometric data that reflect the target's current metabolic level, cardiovascular load, and nervous tension, including but not limited to heart rate, heart rate variability, skin conductance, blood oxygen saturation, and respiratory rate. While the target is moving, the system continuously activates the data acquisition channel, establishing a connection with the sensor device worn by the target via a wireless transmission protocol, and continuously reading the aforementioned real-time physiological parameters at the preset sampling frequency. During this process, the system not only records the values ​​at individual moments but also simultaneously records the timestamps of the data generation to ensure the temporal integrity of the data.

[0097] To specifically implement this step, the system can employ wearable monitoring technology based on photoplethysmography (PPG). The system controls LEDs on the wearable device to emit beams of light at a specific wavelength onto the target's skin and uses a photosensor to receive the reflected light signal. Since changes in blood volume affect light absorption, the system calculates heart rate and blood oxygen saturation data by processing the periodic changes in reflected light intensity. Another approach utilizes bioelectrical impedance analysis (BIA). The system applies a safe, weak alternating current to the body through microelectrodes on the wearable device and measures changes in the body's tissue electrical impedance. Because perspiration and skin conductivity vary under different physiological pressures, the system can analyze changes in impedance data to acquire parameters such as skin conductance and respiratory rate in real time. Both methods can acquire raw signals at high-frequency sampling (e.g., 50Hz or higher) and convert analog signals into digital signals via a built-in analog-to-digital converter before transmitting them to the processing unit.

[0098] S202. Based on the real-time physiological parameter change trend and the time difference between the current time and the scheduled start time of the second duty mission, calculate the predicted value of the target object's physiological parameters at the scheduled start time.

[0099] The system calculates the predicted values ​​of the target object's physiological parameters at the predetermined start time based on the changing trends of real-time physiological parameters and the time difference between the current time and the predetermined start time of the second duty mission. Specifically, this includes: calculating the difference between the predetermined start time and the current time to obtain the remaining recovery time; extracting real-time physiological parameters within the most recent preset time period to construct a physiological parameter time series; performing linear regression analysis on the physiological parameter time series to obtain the recovery rate slope characterizing the changing trend; and using the real-time physiological parameters at the current time as a benchmark, performing linear extrapolation calculations using the recovery rate slope and the remaining recovery time to obtain the predicted values ​​of the target object's physiological parameters at the predetermined start time.

[0100] The system first defines the trend of change as the slope or fluctuation pattern of the physiological parameters over time, representing the speed of the body's recovery or fatigue accumulation. The current time is the system time for this calculation operation, and the scheduled start time of the second duty task is the time specified in the duty schedule when the next task must begin. The time difference is the scalar difference between the two, representing the remaining adjustable window. The predicted physiological parameter value is the physiological indicator value that the target object may reach at a specific future time point (i.e., the scheduled start time), deduced by the system based on current and historical data. The remaining recovery time is the aforementioned time difference. The physiological parameter time series is a set of historical physiological parameters arranged in chronological order. The recovery rate slope is a quantitative indicator of the change in physiological parameters per unit time, obtained through mathematical fitting. When the system performs this step, it first calculates the difference between the predetermined start time and the current time to obtain the remaining recovery time; then it extracts all real-time physiological parameters from the database within the nearest preset time period (e.g., the past 5 minutes) to construct a physiological parameter time series; next, it performs linear regression analysis on the series and calculates the slope of the best-fit line as the recovery rate slope; finally, using the real-time physiological parameter value at the current time as the base point, it calculates the predicted value of the physiological parameters of the target object at the predetermined start time by multiplying the recovery rate slope by the remaining recovery time and through the mathematical logic of linear extrapolation.

[0101] To refine the technical solutions in this step, particularly linear regression analysis and extrapolation calculations, the system can employ the least squares algorithm. The system constructs a linear equation model with time as the independent variable and physiological parameters as the dependent variable. By minimizing the sum of squares of the vertical distances from all observed data points to the fitted line, the regression coefficients (i.e., the slope and intercept) are solved. This slope represents the current recovery rate. Subsequently, the system substitutes the remaining recovery time into the linear equation to calculate the future dependent variable value. Another implementation method is to use the Theil-Sen Estimator algorithm. The system calculates all possible slopes of the straight line connecting any two points in the time series and takes the median of these slopes as the final recovery rate slope. Compared to ordinary least squares, this method is more robust to outliers (such as sudden data changes caused by brief sensor malfunctions). The system uses this median slope in conjunction with the current baseline value for extrapolation calculations, obtaining more robust prediction results and avoiding significant interference from individual noisy data on the prediction trend.

[0102] S203. If the predicted value of the physiological parameter is not within the range of the threshold limit of the admission physiological indicator, then generate an intervention control instruction for the physical passage path.

[0103] The system defines the threshold range of the admission physiological indicators as a pre-set safe range of physiological parameters allowed for the execution of the second duty task. This range typically includes an upper threshold and a lower threshold, such as a heart rate not exceeding a specific value and mental focus not falling below a specific value. There is a logical constraint relationship between the thresholds; that is, the upper threshold must be greater than the lower threshold. The intervention control command is a logical trigger signal generated internally by the system, designed to initiate subsequent auxiliary adjustment processes. The physical travel path refers to the route currently being traveled by the target object. After obtaining the predicted values ​​of physiological parameters calculated by S202, the system compares them with the admission physiological indicator thresholds. If the predicted value is higher than the upper threshold (e.g., a predicted heart rate that is too high, indicating an inability to return to calm) or lower than the lower threshold (e.g., a predicted arousal that is too low, indicating potential drowsiness), the system determines that the target object's state is not up to standard when reaching the next task point. At this time, the system triggers a logical judgment mechanism to generate an intervention control command for the physical travel path. This command carries the target object's identification and the type of parameters to be adjusted, used to activate subsequent augmented reality device adjustments and environmental control processes.

[0104] For the specific implementation of this step, the system can employ a threshold comparison technique based on a rule engine. The system maintains a state mapping table in memory, defining physiological admission standards for different task types (e.g., "sentinel mission" corresponds to a heart rate range of 60-100 bpm, and "patrol mission" corresponds to a heart rate range of 60-120 bpm). The system indexes the specific threshold pair based on the type of the second duty task and uses a numerical comparator circuit or software logic to determine whether the predicted value falls outside the range. Once the comparison result is true (i.e., out of bounds), the rule engine immediately instantiates an intervention control instruction object. Another implementation method is a comprehensive evaluation technique based on fuzzy logic. The system does not rely solely on a single hard threshold but defines a membership function that defines the "probability of failing to meet the standard in the future under the current state." The system inputs the deviation between the predicted value and the standard value and calculates a risk score using a fuzzy inference engine. When the risk score exceeds a preset trigger line, the system determines that intervention is needed and generates an instruction. This method can handle fuzzy situations at the critical edge and avoids frequent false triggers caused by hard thresholds.

[0105] S204. In response to the intervention control command, reduce the information display density of the augmented reality device worn by the target object, and adjust the display color temperature parameters of the augmented reality device;

[0106] The system defines augmented reality devices as smart glasses or helmet displays worn by the target object, capable of displaying digital information overlay. Information display density refers to the number and complexity of visual elements such as virtual graphics, text, and icons presented within a unit field of view. Display color temperature parameter refers to the overall color tendency of the displayed image, usually measured in Kelvin (K). Low color temperature corresponds to warm tones (leaning towards yellow and red), while high color temperature corresponds to cool tones (leaning towards bluish and white). Upon receiving the intervention control command generated by S203, the system immediately calls the graphics rendering engine interface of the augmented reality device. The system first executes noise reduction logic, filtering out currently unnecessary auxiliary information (such as secondary road signs, non-urgent notices, and decorative UI), and setting their transparency to full transparency or directly removing them from the rendering queue, thereby significantly reducing information display density and reducing the visual cognitive load on the target object. Simultaneously, the system modifies the global color matrix of the display driver, reducing the gain of the blue channel and increasing the proportion of the red and green channels, adjusting the display color temperature to a preset warm tone value (such as 3000K), and using the principles of color psychology to induce the target object into a soothing and relaxed psychological state.

[0107] For the specific implementation of this step, the system can employ dynamic rendering technology based on layer management. The system divides the AR interface into multiple layers with different priorities, such as a "core task layer," a "navigation assistance layer," an "environment enhancement layer," and a "system notification layer." When responding to intervention commands, the system batch disables the rendering pipelines of low-priority layers via graphics APIs (such as OpenGL or Vulkan), retaining only the core task layer (e.g., necessary path guidance), thereby reducing density. For color temperature adjustment, the system applies a post-processing shader. The system writes a fragment shader program that accepts a color temperature correction vector as a uniform variable input and performs matrix multiplication on the RGB values ​​of each pixel in the final output, thus completing the mapping from cool to warm tones in real time at the GPU level without reloading assets. Another implementation method is a content-adaptive UI reflow technique. Instead of simply hiding layers, the system dynamically loads a "minimalist" UI layout file. This layout file features larger fonts, smaller icons, and wider spacing. Meanwhile, the system adjusts the driving current of the optomechanical hardware (for certain types of microdisplays, such as Micro-LED) to directly change the emission spectrum characteristics at the hardware physical level, thereby achieving color temperature adjustment. This method is more eye-friendly and consumes less energy than software filters.

[0108] S205. While maintaining the execution of intervention control commands, acquire external field-of-view images through augmented reality devices;

[0109] S206. Identify risk targets in the external field of view image and determine the current environmental safety level of the target object;

[0110] The system identifies risk targets in the external field of view image and determines the current environmental safety level of the target object. Specifically, this includes: processing the external field of view image using a pre-trained target detection model; if a target of a preset category or a dynamic target with a moving speed exceeding a preset safety threshold is identified in the external field of view image, the environmental safety level is determined to be an alarm state; if no target or dynamic target is identified in the external field of view image, the environmental safety level is determined to be a safe state.

[0111] The system defines the external field of view image as real-time video frames or continuous static images captured by the front-facing camera on the augmented reality device, covering the current field of view directly in front of the target object. Maintaining the execution of intervention control commands means that the AR glasses are currently in a low-density, warm-color-temperature display mode, designed to aid in recovery, but the system's perception module cannot be shut down. While maintaining the "subtraction" on the display side, the system continuously "adds" on the perception side. The system activates the image sensor (such as a CMOS or CCD sensor) built into the augmented reality device, independently of the display rendering thread, to start a background video stream acquisition thread. This thread continuously captures ambient light signals at a preset frame rate (such as 30fps) and converts them into a digital image matrix. The system ensures that this acquisition process runs silently in the background and does not display the acquired image on the AR glasses' screen to avoid increasing the visual burden on the target object, but the acquired data is sent to the system's computing unit for subsequent analysis.

[0112] For the specific implementation of this step, the system can employ multi-sensor fusion visual acquisition technology. The system not only utilizes the AR device's main RGB camera to acquire visible light images but also simultaneously activates a depth camera (such as a ToF sensor or a binocular structured light module). The system simultaneously reads RGB frames and depth frames through a Hardware Abstraction Layer (HAL), aligns them, and encapsulates them into an RGB-D image data packet containing color and distance information. This approach provides three-dimensional spatial perception capabilities for subsequent risk identification. Another implementation method is to use intelligent acquisition technology based on regions of interest (ROI). To reduce power consumption and computational load, the system acquires the entire field of view at full resolution. The system utilizes a low-power coprocessor to first analyze low-resolution thumbnails, detecting the presence of high-frequency texture variation regions (typically corresponding to object edges or motion). Only when a potential change is detected does the system instruct the main image sensor to capture and transmit a high-resolution image of the specific region, thereby efficiently acquiring external field-of-view images.

[0113] S207. If the environmental safety level is alarm state, then generate an interrupt command;

[0114] The system defines risk target identification as the process of locating and classifying potential threat objects from images using computer vision technology. Environmental security level is a quantitative rating of the current environmental threat level, divided into alarm state and safe state. Alarm state corresponds to the presence of a threat, and safe state corresponds to no threat. The pre-trained target detection model is a neural network model built on deep learning algorithms and whose parameters have been optimized on a large number of labeled datasets. Preset target categories include, but are not limited to, static or dynamic entities such as enemy personnel, weapons and equipment, and dangerous animals. Dynamic targets refer to objects that move between consecutive frames. The preset safety threshold is an upper limit set for the movement speed of dynamic targets. When the system performs this step, the external field of view image acquired in S205 is input into the pre-trained target detection model. The model outputs the object category labels, confidence scores, and bounding box coordinates contained in the image. The system first checks whether it has identified sensitive targets of the preset category (such as firearms). Secondly, the system calculates the target's movement speed by comparing the target's displacement in consecutive frames and determines whether it exceeds the preset safety threshold (such as a fast-running person). If a sensitive target or a speeding target is identified, the system determines the environmental safety level to be alarm state; if neither is identified, the system determines the environment to be safe.

[0115] To refine the technical solutions in this step, particularly in utilizing pre-trained models for recognition and speed determination, the system can employ a single-stage object detection algorithm based on convolutional neural networks (CNNs), such as the YOLO (You Only LookOnce) series or SSD (Single Shot MultiBox Detector). This model achieves its functionality by containing multiple convolutional layers, capable of extracting image features such as edges, textures, and shapes layer by layer, and mapping these features to object category probabilities and location coordinates through fully connected layers or convolutional prediction layers. The system scales the image to the model input size and directly outputs the detection results after forward propagation. For speed calculation, the system utilizes Kalman filtering or optical flow. The system tracks feature points of the same target across consecutive frames, calculates its pixel displacement, and combines camera intrinsic parameters and depth information (if available) to map the pixel velocity to physical space velocity. Another implementation approach is to use a visual model based on the Transformer architecture (such as DETR). This model utilizes a self-attention mechanism to process image feature sequences, enabling it to better capture global contextual information and achieve higher target recognition rates in complex occlusion environments. For dynamic target detection, the system can use background subtraction to build a background model and extract the foreground motion region, determining the movement speed by calculating the displacement vector of the foreground region's centroid.

[0116] S208. In response to the interrupt command, stop executing the intervention control command and restore the information display density and display color temperature parameters of the augmented reality device to their initial state;

[0117] The system defines the interrupt command as a control signal with the highest system priority. Its function is to forcibly terminate the currently ongoing auxiliary adjustment process and switch the system state to emergency response mode. When the S206 judgment result is an alarm state, it indicates that there is a potential physical threat (such as enemy attack, high-speed approaching vehicles, etc.) around the target object. At this time, physiological recovery is no longer the primary task; survival and combat preparation become the top priority. After the system logic core detects that the security level variable has changed to "alarm," it immediately triggers the interrupt generator. This generator constructs an interrupt command containing an interrupt type code, a trigger source timestamp, and an emergency level identifier, and broadcasts it to all sub-control modules of the system (such as the display control module, audio control module, and environmental interaction module). This command has preemptive transmission rights on the system's internal bus, ensuring that it can be processed immediately.

[0118] For the specific implementation of this step, the system can adopt a message publishing mechanism based on an event-driven architecture. Internally, the system runs a central message bus. When the security assessment service publishes an "alarm state" event, the interrupt controller that has subscribed to the event responds immediately, instantiates an interrupt instruction object, and pushes it to the head of the high-priority command queue. The system scheduler detects a high-priority instruction at the head of the queue and immediately suspends other low-priority tasks. Another implementation method is based on finite state machine (FSM) state transition technology. The system maintains a global state machine containing "monitoring state," "regulation state," and "alarm state." When the input condition "security level = alarm" is met, the state machine forces a transition from the "regulation state" to the "alarm state." At the instant the transition occurs (OnStateChange), the system automatically triggers the bound action function, which is responsible for generating and distributing interrupt instructions. This approach internalizes instruction generation as part of the state transition, ensuring logical rigor.

[0119] S209. Send an adjustment signal to the environmental control equipment located on the physical passageway to control the environmental control equipment to reduce the brightness of the light or output white noise.

[0120] The system defines stopping the execution of intervention control commands as revoking all restrictions and modifications imposed in S204. The initial state refers to the default operating configuration of the augmented reality device before entering adjustment mode, typically a combat or routine duty mode with full information display and a standard high-contrast color temperature (e.g., 6500K or higher). Upon receiving the interrupt command from S207, the system immediately terminates the current "relaxation guidance" process. The system first unlocks the masked UI layer, re-renders all tactical data, navigation information, and key elements such as teammate positions, restoring high-density information display to provide comprehensive battlefield situational awareness. Simultaneously, the system resets the display-driven color matrix, removes warm-toned filters, and instantly switches the color temperature back to cool tones or standard white light, utilizing the stimulating effect of cool light on the optic nerve to help targets quickly increase their alertness.

[0121] For the specific implementation of this step, the system can employ a configuration snapshot rollback technique. Before the system executes S204, it serializes and stores the current UI layout configuration, layer transparency parameters, RGB gain values, and other state data in a "snapshot" stack in memory. When responding to an interrupt command, the system directly pops this snapshot data from the top of the stack, deserializes it, and applies it to the current rendering engine, thus achieving one-click accurate restoration. Another implementation method is to load a preset "combat / alarm configuration document." The system predefines standard configuration templates (Profiles) for various scenarios. When responding to an interrupt, the system directly calls the "Combat_Profile" template, which hardcodes parameters such as enabling all layers, setting the color temperature to 7500K, and setting the brightness to maximum. The system applies this template to override the current dynamically adjusted parameters. This method is more reliable than rollback because it ensures that the restored state is an absolutely standard combat state, rather than some intermediate state that may have existed before.

[0122] In the above embodiments, by collecting physiological parameters in real time and analyzing their changing trends, and combining the time difference to calculate the predicted values ​​of physiological parameters, dynamic monitoring of the status of on-duty personnel is achieved. When the predicted value exceeds the access threshold range, the system adjusts the display density and color temperature parameters of the augmented reality device, as well as controls the brightness and white noise output of the environmental device, forming a dynamic intervention and adjustment mechanism. This prediction-based proactive intervention method improves the physiological state regulation effect of on-duty personnel during task handover and enhances the targeted nature of state recovery. Through the coordinated adjustment of environmental parameters, the system improves the overall effect of physiological state regulation, enhances the adaptability of on-duty personnel when arriving at the next task point, and strengthens the safety during task handover.

[0123] The system in the embodiments of this invention is described below from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3This is a schematic diagram of the physical device structure of a smart camp service data processing system provided in an embodiment of this application.

[0124] It should be noted that, Figure 3 The structure of the system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0125] like Figure 3 As shown, the system includes a Central Processing Unit (CPU) 301, which can perform various appropriate actions and processes based on a program stored in Read-Only Memory (ROM) 302 or a program loaded from storage portion 308 into Random Access Memory (RAM) 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An Input / Output (I / O) interface 305 is also connected to the bus 304.

[0126] The following components are connected to I / O interface 305: input section 306 including a camera, infrared sensor, etc.; output section 307 including a liquid crystal display (LCD) and speakers, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card and a modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0127] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the various functions defined in the present invention.

[0128] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. The transmitted data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0130] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the system described in the above embodiments; or it may exist independently and not assembled into the system. The storage medium carries one or more computer programs that, when executed by a processor of a system, cause the system to implement the methods provided in the above embodiments.

[0131] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0132] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0133] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0134] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for processing duty data of a smart police station, characterized in that, include: Obtain the first task attribute set of the first duty task currently being executed and the second task attribute set of the second duty task to be executed. The first task attribute set includes the end position of the first task and the task type identifier, and the second task attribute set includes the start position of the second task, the task type identifier, and the latest start time. A completion status vector is generated based on the first task attribute set, the completion status vector consisting of a first equipment holding list and a first physiological load level; an admission requirement vector is generated based on the second task attribute set, the admission requirement vector consisting of a second equipment requirement list and a second physiological load limit. The completion state vector is compared with the admission requirement vector to determine state conflict items, including equipment mismatch items or physiological load exceeding limits. Based on the state conflict item, the corresponding state recovery action is matched from the preset duty transition rule table, and the state transition time required to execute the state recovery action is obtained; Calculate the physical passage time based on the end position of the first task and the start position of the second task; The sum of the state transition duration and the physical passage duration is determined as the comprehensive transition time window; The critical disengagement time of the first task is calculated by subtracting the comprehensive transition time window from the latest start time of the second task. Obtain the estimated completion time of the first service task. If the estimated completion time is earlier than or equal to the critical departure time, generate a scheduling instruction that includes the state recovery action, and lock the second service task as the next execution item.

2. The method of claim 1, wherein, The step of generating a completion status vector based on the first task attribute set specifically includes: The task duration and environmental stress parameters are parsed from the first task attribute set. The environmental stress parameters include the temperature value and noise decibel value of the task area. Using a preset physiological energy consumption accumulation model, the basal metabolic rate corresponding to the task type identifier is used as the base, the environmental stress parameter is mapped to a nonlinear gain coefficient, and the task duration is integrated to obtain the cumulative fatigue value. The accumulated fatigue values ​​are mapped to a preset fatigue grading table to determine the first physiological load level; The first physiological load level is combined with the list of standard equipment retrieved based on the task type identifier to generate a completion status vector.

3. The method of claim 1, wherein, The step of generating a completion status vector based on the first task attribute set specifically includes: Obtain the initial equipment list for the first duty mission, and classify the items in the initial equipment list into consumable equipment items and carry-on equipment items according to the mission type identifier. Execute the equipment state inheritance logic to remove the consumable equipment item from the initial equipment list, retaining only the held equipment item; Detect the regional attribute of the end location of the first task. If the regional attribute is marked as a contaminated area or a classified area, then attach a corresponding status handling label to the possessed equipment item. The first equipment holding list is generated by removing and tagging the held equipment items, and then combined with the first physiological load level to form a completion status vector.

4. The method of claim 1, wherein, After locking the second service task as the next execution item, the method further includes: When the target object performs the physical passage, the real-time physiological parameters of the target object are acquired at a preset sampling frequency; Based on the changing trend of the real-time physiological parameters and the time difference between the current time and the predetermined start time of the second duty task, the predicted value of the physiological parameters of the target object at the predetermined start time is calculated. If the predicted value of the physiological parameter is not within the range limited by the threshold of the access physiological indicator, then an intervention control instruction is generated for the physical access path; In response to the intervention control command, the information display density of the augmented reality device worn by the target object is reduced, and the display color temperature parameter of the augmented reality device is adjusted; An adjustment signal is sent to an environmental control device located on the physical passageway to control the environmental control device to reduce the brightness of the light or output white noise.

5. The method according to claim 4, characterized in that, The step of calculating the predicted physiological parameter value of the target object at the predetermined start time based on the changing trend of the real-time physiological parameters and the time difference between the current time and the predetermined start time of the second duty task specifically includes: Calculate the difference between the predetermined start time and the current time to obtain the remaining recovery time; Extract the real-time physiological parameters within the most recent preset time period to construct a physiological parameter time series; Linear regression analysis was performed on the time series of the physiological parameters to obtain the slope of the recovery rate, which characterizes the trend of change. Based on the real-time physiological parameters at the current moment, linear extrapolation is performed using the recovery rate slope and the remaining recovery time to obtain the predicted physiological parameter values ​​of the target object at the predetermined start time.

6. The method according to claim 4, characterized in that, After responding to the intervention control command by reducing the information display density of the augmented reality device worn by the target object and adjusting the display color temperature parameters of the augmented reality device, the method further includes: While maintaining the execution of the intervention control command, the external field of view image is acquired through the augmented reality device; Risk target identification is performed on the external field of view image to determine the current environmental safety level of the target object; If the environmental safety level is in an alarm state, an interrupt command is generated; In response to the interrupt command, the execution of the intervention control command is stopped, and the information display density and display color temperature parameters of the augmented reality device are restored to their initial state.

7. The method according to claim 6, characterized in that, The step of identifying risk targets in the external field-of-view image and determining the current environmental security level of the target object specifically includes: The external field of view image is processed using a pre-trained object detection model; If a target of a preset category or a dynamic target with a moving speed exceeding a preset safety threshold is identified in the external field of view image, the environmental safety level is determined to be the alarm state. If the target and the dynamic target are not identified in the external field of view image, the environmental safety level is determined to be a safe state.

8. A smart camp service data processing system, characterized in that, The system includes: One or more processors and a memory; the memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the system to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on the system, the system performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the system, the system performs the method as described in any one of claims 1-7.

Images